Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks7 from public data
- 14
- Cross-Scale Self-Supervised Blind Image Deblurring via Implicit Neural Representation10
A self-supervised method for BID that does not require GT images is introduced that significantly outperforms existing self-supervised methods in extensive experiments and proposes an effective cross-scale consistency loss.
- Test-Time Model Adaptation for Image Reconstruction Using Self-supervised Adaptive Layers9
This paper introduces an self-supervised test-time adaptation approach that leverages a pre-trained model on an external dataset and efficiently adapts it to each test sample for optimal generalization performance.
- 4
- ViT-quant: module-specific optimization for post-training quantization of vision transformers–
Experiments on ViT-S, DeiT-S, and Swin-S models show that under INT4 quantization, the accuracy decreases by less than 9% compared with the full-precision model, and the accuracy loss of INT6 quantization is less than 1%.
- Zero-Shot Blind-Spot Image Denoising via Cross-Scale Non-Local Pixel Refilling–
A theoretical analysis quantifying the impact of replacing masked pixels with observations exhibiting weaker noise correlation but potentially reduced similarity is presented, revealing a trade-off that impacts the statistical risk of the estimation.
- Magnetic Resonance Spectroscopy Water Processing Latest Progress–
Two technique, water suppression processing and without suppression water processing are introduced, several other techniques of that are compared and compared and general reflected the latest evolve of this technique nation and aboard are introduced.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.